Deep belief networks based radar signal classification system

  • Chang Min Jeong
  • Young Giu Jung
  • Sang Jo Lee
Original Research


A threat library is used in most of the existing electronic warfare systems to identify or execute jamming against various radar signals. The conventional method uses frequency, pulse repetition interval, and pulse width sampled from the pulse description word column as characteristics of a signal. Such sampling technique cannot effectively model each radar signal when dealing with a complex signal array. In this paper, a new deep belief network model is proposed to generate a more efficient threat library for radar signal classification. The proposed model consists of independent restricted Boltzman machines (RBMs) of frequency, pulse repetition interval, pulse width respectively, and a RBM which fuses the result again. The performance of the existing system and the proposed system is evaluated by testing the signals with measurement errors and insufficient information. As a result, the proposed system shows more than 6% performance improvement over the existing system.


Threat library DBN BP Radar signal classification 


Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.


  1. Anjaneyulu L, Muthy N, Sarma N (2008) Radar emitter classification using self-organizing neural network models. International Conference on MICROWAVEGoogle Scholar
  2. Cho YS, Moon SC (2015) Recommender system using periodicity analysis via mining sequential patterns with time-series and FART analysis. J Converg 6:2Google Scholar
  3. Hinton G, Osindero S, The Y (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554MathSciNetCrossRefzbMATHGoogle Scholar
  4. Jeong CM, Jung YG, Lee SJ (2017) Neural network-based radar signal classification system using probability moment and ApEn. Soft comput. Google Scholar
  5. Keegan N, Ji S-Y, Chaudhary A, Concolato C, Yu B (2016) A survey of cloud-based network intrusion detection analysis. Hum Centric Comput Inf Sci 6:19CrossRefGoogle Scholar
  6. Lee-Urban S, Trewhitt E, Bieder I, Odom J, Boone T, Whitaker E (2015) CORA: a flexible hybrid approach to building cognitive systems. Third annual conference on advances in cognitive systemsGoogle Scholar
  7. Lin CM, Chen YM, Hsueh CS (2014) A self-organizing interval type-2 fuzzy neural network for radar emitter identification. Int J Fuzzy Syst 16(1):20–30Google Scholar
  8. Petrov N, Jordanov I, Nikolov, Roe J (2013) Radar emitter signals recognition and classification with feedforward networks. Procedia Comput Sci 22: 1192–1200. (ISSN 1877–0509)Google Scholar
  9. Pincus S, Gladstone I, Ehrenkranz R (1991) A regularity statistic for medical data analysis. J Clin Monit Comput 7(4):335–345CrossRefGoogle Scholar
  10. Richard G, Wiley (2006) ELINT: the interception and analysis of radar signals. ARTHOUSE, pp 255–412Google Scholar
  11. Sato A, Huang R, Yen NY (2015) Design of fusion technique-based mining engine for smart business. Hum Centric Comput Inf Sci 5:23CrossRefGoogle Scholar
  12. Shieh C, Lin C (2002) A vector neural network for emitter identification. Antennas Propag IEEE Trans, 50(8), 1120–1127CrossRefGoogle Scholar
  13. Zhu B, Wei-dong J (2012) Radar Emitter signal recognition based on EMD and neural network. J Comput 7(6):1413–1420CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Agency for Defense DevelopmentDaejeonRepublic of Korea
  2. 2.YM-NaeultechIncheonRepublic of Korea
  3. 3.Department of Computer EngineeringKyungpook National UniversityDaeguRepublic of Korea

Personalised recommendations